inno-experiment-analysis

This skill should be used when the user asks to "analyze experimental results", "generate results section", "statistical analysis of experiments", "compare model performance", "create results visualization", or mentions connecting experimental data to paper writing. Provides comprehensive guidance for analyzing ML/AI experimental results and generating paper-ready content.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/inno-experiment-analysis/SKILL.md

Quality

Content

46%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is well-structured with clear reference navigation, but it leans on abstract directives ('select appropriate tools') rather than executable code or commands, and contains redundant summary sections that pad the token budget without adding value.

Suggestions

Replace vague directives like 'Select appropriate tools for data loading' and 'Select appropriate statistical tests based on data characteristics' with concrete library calls or decision rules (e.g., scipy.stats.ttest_ind for two-group comparison).

Remove the redundant 'Best Practices Summary' and final 'Summary' sections, which repeat content already covered in 'Common Mistakes and Pitfalls' and the 'Workflow'.

Add explicit validation checkpoints between pipeline steps (e.g., after data loading, confirm schema/units before proceeding to statistical analysis), and create the referenced examples/ directory or remove the dangling references to example-analysis-report.md and example-results-section.md.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but includes repeated material - the 'Best Practices Summary' rehashes the 'Common Mistakes and Pitfalls' section, and the 'Summary' rehashes the workflow already stated, adding padding without new information.	3 / 5
Actionability	Predominantly high-level lists and descriptions rather than executable guidance - phrases like 'Select appropriate tools for data loading', 'Select appropriate statistical tests based on data characteristics', and 'Use appropriate visualization tools' give no concrete code, commands, or library specifics.	2 / 5
Workflow Clarity	A clear six-step pipeline is sequenced and a quality-check checklist exists, but steps lack explicit validation checkpoints between stages; the destructive-capable operations (e.g., overwriting results drafts) have no validate-then-proceed feedback loop.	3 / 5
Progressive Disclosure	Good structure with clearly signaled one-level-deep references to four real files in references/ (statistical-methods.md, results-writing-guide.md, visualization-best-practices.md, common-pitfalls.md); however, the body also references a non-existent examples/ directory and example files, a minor organization gap.	4 / 5
	Total	12 / 20 Passed

Description

96%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong description that explicitly states what the skill does and when to use it, with multiple natural trigger phrases a user would actually say. Its only weakness is slight overlap risk with the related ml-paper-writing skill.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions - 'analyze experimental results', 'generate results section', 'statistical analysis', 'compare model performance', 'create results visualization' - providing comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what ('Provides comprehensive guidance for analyzing ML/AI experimental results and generating paper-ready content') and when ('This skill should be used when the user asks to...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural user phrases including exact quoted triggers ('analyze experimental results', 'generate results section', 'statistical analysis of experiments', 'compare model performance', 'create results visualization') plus the descriptive 'connecting experimental data to paper writing'.	5 / 5
Distinctiveness Conflict Risk	Clear niche (experimental results analysis for ML/AI papers) with distinct triggers; minor overlap risk with a general 'ml-paper-writing' skill it explicitly references, but its analysis/statistics focus keeps it distinguishable.	4 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/inno-experiment-analysis/SKILL.md
Commit: 4b35756

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.